Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4955 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1098555 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4396. Min Act: -0.0000

Data Index: 54959 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1271948 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1764863 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1456225 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4391. Min Act: -0.0000

Data Index: 880802 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1020637 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1877660 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1255843 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1646444 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1990530 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1227886 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3210. Min Act: -0.0000

Data Index: 155986 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1880939 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1764081 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3298. Min Act: -0.0000

Data Index: 196939 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3125. Min Act: -0.0000

Data Index: 307610 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1752765 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2990. Min Act: -0.0000

Data Index: 669177 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3094. Min Act: -0.0000

Data Index: 709109 (The Pile)

Max Activating Token Index: 517